paper-with-me

홈 › Papers

Learning Hierarchical Procedural Memory for LLM Agents through Bayesian Selection and Contrastive Refinement

2025-12-22 · Saman Forouzandeh, Wei Peng, Parham Moradi, Xinghuo Yu, Mahdi Jalili arxiv

We present MACLA, a framework that decouples reasoning from learning by maintaining a frozen large language model while performing all adaptation in an external hierarchical procedural memory. MACLA extracts reusable procedures from trajectories, tracks reliability via Bayesian posteriors, selects actions through expected-utility scoring, and refines procedures by contrasting successes and failures. Across four benchmarks (ALFWorld, WebShop, TravelPlanner, InterCodeSQL), MACLA achieves 78.1 percent average performance, outperforming all baselines. On ALFWorld unseen tasks, MACLA reaches 90.3 percent with 3.1 percent positive generalization. The system constructs memory in 56 seconds, 2800 times faster than the state-of-the-art LLM parameter-training baseline, compressing 2851 trajectories into 187 procedures. Experimental results demonstrate that structured external memory with Bayesian selection and contrastive refinement enables sample-efficient, interpretable, and continually improving agents without LLM parameter updates.

📄 PDF Abstract BibTeX arXiv:2512.18950

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Memp: Exploring Agent Procedural Memory

2025-08-08 · Runnan Fang, Yuan Liang, Xiaobin Wang, Jialong Wu 외 arxiv

Large Language Models (LLMs) based agents excel at diverse tasks, yet they suffer from brittle procedural memory that is manually engineered or entangled in static parameters. In this work, we investigate strategies to e…

Procedural Memory Is Not All You Need: Bridging Cognitive Gaps in LLM-Based Agents

2025-05-06 · Schaun Wheeler, Olivier Jeunen

Large Language Models (LLMs) represent a landmark achievement in Artificial Intelligence (AI), demonstrating unprecedented proficiency in procedural tasks such as text generation, code completion, and conversational cohe…

AllCode CompletionText Generation

AdMem: Advanced Memory for Task-solving Agents

2026-06-05 · Runzhe Wang, Huilin Lu, Shengjie Liu, Li Dong 외 arxiv

Large Language Models (LLMs) show promise as tool-using agents but remain limited in long-horizon tasks that require remembering, organizing, and reusing knowledge. Prior memory approaches aim to resolve the situation, b…

LEGOMem: Modular Procedural Memory for Multi-agent LLM Systems for Workflow Automation

2025-10-06 · Dongge Han, Camille Couturier, Daniel Madrigal Diaz, Xuchao Zhang 외 arxiv

We introduce LEGOMem, a modular procedural memory framework for multi-agent large language model (LLM) systems in workflow automation. LEGOMem decomposes past task trajectories into reusable memory units and flexibly all…

Neural Procedural Memory: Empowering LLM Agents with Implicit Activation Steering

2026-06-29 · Chengfeng Zhao, Yuqiao Tan, Shizhu He, Yequan Wang 외 arxiv

While Large Language Models (LLMs) excel as static solvers, transforming them into autonomous agents remains challenging. This transition requires continuous environmental interaction, yet current agents lack the necessa…